chore: add agent context and refresh new chat icon

.agents/skills/write-tui/DESIGN.md

@@ -83,13 +83,13 @@
  Select a model  (type to search)
  Tab toggle provider · ↑↓ navigate · Enter select · Esc cancel   ← hint 首项即 Tab 切换
                                             ← 空行
- All   Pythinker Code   openai                   ← tab 条：激活项填充背景（primary 底 + text 字 + bold），其余 textMuted
+ All   Pythinker Code   openai                   ← tab bar: active uses selectionBg + inverseText + bold; others use textMuted
                                             ← 空行
   ❯ ...
 ```
 
 - tab 条位置：**在 hint 行下方**，且**上下各一空行**（与 hint、与列表都隔开）。
-- 激活 tab：`chalk.bgHex(colors.primary).hex(colors.text).bold(\` ${label} \`)`；非激活：`chalk.hex(colors.textMuted)`。两者可见宽度一致，切换不抖动。
+- Active tab: `chalk.bgHex(colors.selectionBg).hex(colors.inverseText).bold(\` ${label} \`)`; inactive tab: `chalk.hex(colors.textMuted)`. Both have the same visible width.
 - 第一个 tab 恒为 `All`（聚合所有 provider）；**默认停在 `All`**。仅当显式传 `initialTabId`（如 `/provider` 新增完跳转）才停在指定 provider tab。
 - `Tab` / `Shift+Tab` 循环切换；hint 行首项即 `Tab toggle provider`。
 - 当前模型在所在 tab 内仍以 `❯` + ` ← current` 标记，切 tab 不丢失定位。

.changeset/calm-doctors-check.md

@@ -0,0 +1,5 @@
+---
+"@pymodel/pythinker-code": patch
+---
+
+Make `pythinker doctor` validate `config.toml` with the current schema in every engine mode.

.changeset/refresh-cli-tui.md

@@ -0,0 +1,5 @@
+---
+"@pymodel/pythinker-code": patch
+---
+
+Update the terminal interface colors, transcript hierarchy, welcome panel, and workflow progress states.

.changeset/refreshed-new-chat-icon.md

@@ -0,0 +1,5 @@
+---
+"@pymodel/pythinker-code": patch
+---
+
+Use a refreshed New Chat icon across desktop and mobile navigation.

.changeset/workspace-file-explorer.md

@@ -0,0 +1,5 @@
+---
+"@pymodel/pythinker-code": minor
+---
+
+Add a sidebar Explorer for browsing and opening workspace files.

CONTEXT.md

@@ -0,0 +1,69 @@
+# Pythinker Code
+
+Pythinker Code is a provider-agnostic AI coding agent for terminal, browser, desktop, and editor workflows.
+
+## Language
+
+**Expert Talk**:
+A structured conversation between two user-selected AI models that returns one fused answer.
+_Avoid_: Debate mode, fusion mode
+
+**Expert Talk pair**:
+The two ordered configured model IDs saved for future Expert Talk runs.
+_Avoid_: Global pair, secondary model
+
+**Configured model ID**:
+The stable catalog key that identifies one configured model record and can be stored in an Expert Talk pair.
+_Avoid_: Display name, provider model name, loose alias
+
+**Effective model binding**:
+The immutable execution identity produced for one Expert Talk role after current catalog and routing validation.
+_Avoid_: Selected model, live alias
+
+**Pair collapse**:
+An Expert Talk admission failure where two configured selections resolve to the same effective execution target.
+_Avoid_: Duplicate model choice
+
+**Expert Talk admission**:
+The pre-acceptance validation that resolves and freezes an eligible, distinct pair for one run.
+_Avoid_: Provider ping, opening stage
+
+**Fusion Lead**:
+The first model in an Expert Talk pair. It participates as an equal expert, then its immutable model binding supplies a fresh inference for fusion.
+_Avoid_: Architect, judge, Model 1
+
+**Peer Expert**:
+The second model in an Expert Talk pair. It participates as an equal expert in opening and peer review but does not own fusion.
+_Avoid_: Secondary model, Model 2
+
+**Expert Talk activation**:
+The transient intent to use Expert Talk for the next accepted user turn.
+_Avoid_: Expert Talk mode, persistent activation
+
+**Expert Talk run**:
+One recorded Expert Talk execution owned by one accepted user turn.
+_Avoid_: Resumed run, shared run
+
+**Expert Talk exchange**:
+Two independent openings followed by one symmetric peer review between the run-scoped Fusion Lead and Peer Expert.
+_Avoid_: Debate, adaptive conversation
+
+**Fused answer**:
+The single direct response produced by a fresh Fusion Lead inference after the Expert Talk exchange.
+_Avoid_: Verdict, winning answer
+
+**Fusion notes**:
+Structured consensus, divergence, uncertainty, and attribution stored with an Expert Talk run but excluded from the normal assistant answer.
+_Avoid_: Diagnostic appendix, debate transcript
+
+**Expert Talk stage artifact**:
+An immutable complete or partial opening, review, or fusion output owned by one role and stage and kept outside the normal transcript.
+_Avoid_: Participant message, hidden memory
+
+**Expert Talk result**:
+The versioned successful-run record that contains the fused answer and separate fusion notes.
+_Avoid_: Meeting transcript, winning opinion
+
+**Expert Talk retry**:
+A new run for the same accepted turn input that reruns admission and every stage without resuming participants or reusing artifacts.
+_Avoid_: Resume, fusion-only retry

apps/pythinker-code/dist-web/.web-bundle-manifest.json

@@ -1,4 +1,4 @@
 {
-  "sourceHash": "4c25680541a5da27d1f06c12171abdcee797d428d042d4583a4a6ed94d7db4e1",
-  "sourceFileCount": 410
+  "sourceHash": "09c4da42042f6a0112a3baa1aecd6062c9f46f6e848edab9c077c2076bfdf819",
+  "sourceFileCount": 411
 }